diff options
Diffstat (limited to 'mllib')
19 files changed, 55 insertions, 57 deletions
diff --git a/mllib/src/main/scala/org/apache/spark/ml/Pipeline.scala b/mllib/src/main/scala/org/apache/spark/ml/Pipeline.scala index d18fb69799..195a93e086 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/Pipeline.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/Pipeline.scala @@ -212,7 +212,7 @@ object Pipeline extends MLReadable[Pipeline] { } } - /** Methods for [[MLReader]] and [[MLWriter]] shared between [[Pipeline]] and [[PipelineModel]] */ + /** Methods for `MLReader` and `MLWriter` shared between [[Pipeline]] and [[PipelineModel]] */ private[ml] object SharedReadWrite { import org.json4s.JsonDSL._ diff --git a/mllib/src/main/scala/org/apache/spark/ml/Predictor.scala b/mllib/src/main/scala/org/apache/spark/ml/Predictor.scala index 569a5fb993..e29d7f48a1 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/Predictor.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/Predictor.scala @@ -165,7 +165,7 @@ abstract class PredictionModel[FeaturesType, M <: PredictionModel[FeaturesType, } /** - * Transforms dataset by reading from [[featuresCol]], calling [[predict()]], and storing + * Transforms dataset by reading from [[featuresCol]], calling `predict`, and storing * the predictions as a new column [[predictionCol]]. * * @param dataset input dataset diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/Classifier.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/Classifier.scala index e35b04a1cf..6decea7271 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/classification/Classifier.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/classification/Classifier.scala @@ -50,7 +50,7 @@ private[spark] trait ClassifierParams * Single-label binary or multiclass classification. * Classes are indexed {0, 1, ..., numClasses - 1}. * - * @tparam FeaturesType Type of input features. E.g., [[Vector]] + * @tparam FeaturesType Type of input features. E.g., `Vector` * @tparam E Concrete Estimator type * @tparam M Concrete Model type */ @@ -134,7 +134,7 @@ abstract class Classifier[ * Model produced by a [[Classifier]]. * Classes are indexed {0, 1, ..., numClasses - 1}. * - * @tparam FeaturesType Type of input features. E.g., [[Vector]] + * @tparam FeaturesType Type of input features. E.g., `Vector` * @tparam M Concrete Model type */ @DeveloperApi @@ -151,7 +151,7 @@ abstract class ClassificationModel[FeaturesType, M <: ClassificationModel[Featur * Transforms dataset by reading from [[featuresCol]], and appending new columns as specified by * parameters: * - predicted labels as [[predictionCol]] of type [[Double]] - * - raw predictions (confidences) as [[rawPredictionCol]] of type [[Vector]]. + * - raw predictions (confidences) as [[rawPredictionCol]] of type `Vector`. * * @param dataset input dataset * @return transformed dataset diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala index 082848c9de..71293017e0 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala @@ -36,7 +36,7 @@ import org.apache.spark.sql.Dataset /** - * [[http://en.wikipedia.org/wiki/Decision_tree_learning Decision tree]] learning algorithm + * Decision tree learning algorithm (http://en.wikipedia.org/wiki/Decision_tree_learning) * for classification. * It supports both binary and multiclass labels, as well as both continuous and categorical * features. @@ -135,7 +135,7 @@ object DecisionTreeClassifier extends DefaultParamsReadable[DecisionTreeClassifi } /** - * [[http://en.wikipedia.org/wiki/Decision_tree_learning Decision tree]] model for classification. + * Decision tree model (http://en.wikipedia.org/wiki/Decision_tree_learning) for classification. * It supports both binary and multiclass labels, as well as both continuous and categorical * features. */ diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala index 5946a12933..ba70293273 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala @@ -40,7 +40,7 @@ import org.apache.spark.sql.functions._ import org.apache.spark.sql.types.DoubleType /** - * [[http://en.wikipedia.org/wiki/Gradient_boosting Gradient-Boosted Trees (GBTs)]] + * Gradient-Boosted Trees (GBTs) (http://en.wikipedia.org/wiki/Gradient_boosting) * learning algorithm for classification. * It supports binary labels, as well as both continuous and categorical features. * Note: Multiclass labels are not currently supported. @@ -158,7 +158,7 @@ object GBTClassifier extends DefaultParamsReadable[GBTClassifier] { } /** - * [[http://en.wikipedia.org/wiki/Gradient_boosting Gradient-Boosted Trees (GBTs)]] + * Gradient-Boosted Trees (GBTs) (http://en.wikipedia.org/wiki/Gradient_boosting) * model for classification. * It supports binary labels, as well as both continuous and categorical features. * Note: Multiclass labels are not currently supported. @@ -233,8 +233,8 @@ class GBTClassificationModel private[ml]( * The importance vector is normalized to sum to 1. This method is suggested by Hastie et al. * (Hastie, Tibshirani, Friedman. "The Elements of Statistical Learning, 2nd Edition." 2001.) * and follows the implementation from scikit-learn. - * - * @see [[DecisionTreeClassificationModel.featureImportances]] + + * See `DecisionTreeClassificationModel.featureImportances` */ @Since("2.0.0") lazy val featureImportances: Vector = TreeEnsembleModel.featureImportances(trees, numFeatures) diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala index 4bab801bb3..1fed5fd429 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala @@ -863,10 +863,10 @@ class BinaryLogisticRegressionSummary private[classification] ( * Returns the receiver operating characteristic (ROC) curve, * which is a Dataframe having two fields (FPR, TPR) * with (0.0, 0.0) prepended and (1.0, 1.0) appended to it. + * See http://en.wikipedia.org/wiki/Receiver_operating_characteristic * - * Note: This ignores instance weights (setting all to 1.0) from [[LogisticRegression.weightCol]]. + * Note: This ignores instance weights (setting all to 1.0) from `LogisticRegression.weightCol`. * This will change in later Spark versions. - * @see http://en.wikipedia.org/wiki/Receiver_operating_characteristic */ @Since("1.5.0") @transient lazy val roc: DataFrame = binaryMetrics.roc().toDF("FPR", "TPR") @@ -874,7 +874,7 @@ class BinaryLogisticRegressionSummary private[classification] ( /** * Computes the area under the receiver operating characteristic (ROC) curve. * - * Note: This ignores instance weights (setting all to 1.0) from [[LogisticRegression.weightCol]]. + * Note: This ignores instance weights (setting all to 1.0) from `LogisticRegression.weightCol`. * This will change in later Spark versions. */ @Since("1.5.0") @@ -884,7 +884,7 @@ class BinaryLogisticRegressionSummary private[classification] ( * Returns the precision-recall curve, which is a Dataframe containing * two fields recall, precision with (0.0, 1.0) prepended to it. * - * Note: This ignores instance weights (setting all to 1.0) from [[LogisticRegression.weightCol]]. + * Note: This ignores instance weights (setting all to 1.0) from `LogisticRegression.weightCol`. * This will change in later Spark versions. */ @Since("1.5.0") @@ -893,7 +893,7 @@ class BinaryLogisticRegressionSummary private[classification] ( /** * Returns a dataframe with two fields (threshold, F-Measure) curve with beta = 1.0. * - * Note: This ignores instance weights (setting all to 1.0) from [[LogisticRegression.weightCol]]. + * Note: This ignores instance weights (setting all to 1.0) from `LogisticRegression.weightCol`. * This will change in later Spark versions. */ @Since("1.5.0") @@ -906,7 +906,7 @@ class BinaryLogisticRegressionSummary private[classification] ( * Every possible probability obtained in transforming the dataset are used * as thresholds used in calculating the precision. * - * Note: This ignores instance weights (setting all to 1.0) from [[LogisticRegression.weightCol]]. + * Note: This ignores instance weights (setting all to 1.0) from `LogisticRegression.weightCol`. * This will change in later Spark versions. */ @Since("1.5.0") @@ -919,7 +919,7 @@ class BinaryLogisticRegressionSummary private[classification] ( * Every possible probability obtained in transforming the dataset are used * as thresholds used in calculating the recall. * - * Note: This ignores instance weights (setting all to 1.0) from [[LogisticRegression.weightCol]]. + * Note: This ignores instance weights (setting all to 1.0) from `LogisticRegression.weightCol`. * This will change in later Spark versions. */ @Since("1.5.0") diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/ProbabilisticClassifier.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/ProbabilisticClassifier.scala index 59277d0f42..88642abf63 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/classification/ProbabilisticClassifier.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/classification/ProbabilisticClassifier.scala @@ -45,7 +45,7 @@ private[classification] trait ProbabilisticClassifierParams * * Single-label binary or multiclass classifier which can output class conditional probabilities. * - * @tparam FeaturesType Type of input features. E.g., [[Vector]] + * @tparam FeaturesType Type of input features. E.g., `Vector` * @tparam E Concrete Estimator type * @tparam M Concrete Model type */ @@ -70,7 +70,7 @@ abstract class ProbabilisticClassifier[ * Model produced by a [[ProbabilisticClassifier]]. * Classes are indexed {0, 1, ..., numClasses - 1}. * - * @tparam FeaturesType Type of input features. E.g., [[Vector]] + * @tparam FeaturesType Type of input features. E.g., `Vector` * @tparam M Concrete Model type */ @DeveloperApi @@ -89,8 +89,8 @@ abstract class ProbabilisticClassificationModel[ * Transforms dataset by reading from [[featuresCol]], and appending new columns as specified by * parameters: * - predicted labels as [[predictionCol]] of type [[Double]] - * - raw predictions (confidences) as [[rawPredictionCol]] of type [[Vector]] - * - probability of each class as [[probabilityCol]] of type [[Vector]]. + * - raw predictions (confidences) as [[rawPredictionCol]] of type `Vector` + * - probability of each class as [[probabilityCol]] of type `Vector`. * * @param dataset input dataset * @return transformed dataset @@ -210,7 +210,7 @@ private[ml] object ProbabilisticClassificationModel { /** * Normalize a vector of raw predictions to be a multinomial probability vector, in place. * - * The input raw predictions should be >= 0. + * The input raw predictions should be nonnegative. * The output vector sums to 1, unless the input vector is all-0 (in which case the output is * all-0 too). * diff --git a/mllib/src/main/scala/org/apache/spark/ml/evaluation/Evaluator.scala b/mllib/src/main/scala/org/apache/spark/ml/evaluation/Evaluator.scala index dfbc3e5222..e7b949ddce 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/evaluation/Evaluator.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/evaluation/Evaluator.scala @@ -53,7 +53,7 @@ abstract class Evaluator extends Params { def evaluate(dataset: Dataset[_]): Double /** - * Indicates whether the metric returned by [[evaluate()]] should be maximized (true, default) + * Indicates whether the metric returned by `evaluate` should be maximized (true, default) * or minimized (false). * A given evaluator may support multiple metrics which may be maximized or minimized. */ diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/ChiSqSelector.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/ChiSqSelector.scala index bd053e886f..1482eb3d1f 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/feature/ChiSqSelector.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/feature/ChiSqSelector.scala @@ -42,8 +42,8 @@ private[feature] trait ChiSqSelectorParams extends Params /** * Number of features that selector will select (ordered by statistic value descending). If the - * number of features is < numTopFeatures, then this will select all features. The default value - * of numTopFeatures is 50. + * number of features is less than numTopFeatures, then this will select all features. + * The default value of numTopFeatures is 50. * @group param */ final val numTopFeatures = new IntParam(this, "numTopFeatures", diff --git a/mllib/src/main/scala/org/apache/spark/ml/param/params.scala b/mllib/src/main/scala/org/apache/spark/ml/param/params.scala index e7780cf1c3..9245931b27 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/param/params.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/param/params.scala @@ -552,7 +552,7 @@ trait Params extends Identifiable with Serializable { * * This only needs to check for interactions between parameters. * Parameter value checks which do not depend on other parameters are handled by - * [[Param.validate()]]. This method does not handle input/output column parameters; + * `Param.validate()`. This method does not handle input/output column parameters; * those are checked during schema validation. * @deprecated Will be removed in 2.1.0. All the checks should be merged into transformSchema */ @@ -580,8 +580,7 @@ trait Params extends Identifiable with Serializable { } /** - * Explains all params of this instance. - * @see [[explainParam()]] + * Explains all params of this instance. See `explainParam()`. */ def explainParams(): String = { params.map(explainParam).mkString("\n") @@ -678,7 +677,7 @@ trait Params extends Identifiable with Serializable { /** * Sets default values for a list of params. * - * Note: Java developers should use the single-parameter [[setDefault()]]. + * Note: Java developers should use the single-parameter `setDefault`. * Annotating this with varargs can cause compilation failures due to a Scala compiler bug. * See SPARK-9268. * @@ -712,8 +711,7 @@ trait Params extends Identifiable with Serializable { /** * Creates a copy of this instance with the same UID and some extra params. * Subclasses should implement this method and set the return type properly. - * - * @see [[defaultCopy()]] + * See `defaultCopy()`. */ def copy(extra: ParamMap): Params @@ -730,7 +728,8 @@ trait Params extends Identifiable with Serializable { /** * Extracts the embedded default param values and user-supplied values, and then merges them with * extra values from input into a flat param map, where the latter value is used if there exist - * conflicts, i.e., with ordering: default param values < user-supplied values < extra. + * conflicts, i.e., with ordering: + * default param values less than user-supplied values less than extra. */ final def extractParamMap(extra: ParamMap): ParamMap = { defaultParamMap ++ paramMap ++ extra diff --git a/mllib/src/main/scala/org/apache/spark/ml/recommendation/ALS.scala b/mllib/src/main/scala/org/apache/spark/ml/recommendation/ALS.scala index a2c4c26911..02e2384afe 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/recommendation/ALS.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/recommendation/ALS.scala @@ -99,7 +99,7 @@ private[recommendation] trait ALSParams extends ALSModelParams with HasMaxIter w with HasPredictionCol with HasCheckpointInterval with HasSeed { /** - * Param for rank of the matrix factorization (>= 1). + * Param for rank of the matrix factorization (positive). * Default: 10 * @group param */ @@ -109,7 +109,7 @@ private[recommendation] trait ALSParams extends ALSModelParams with HasMaxIter w def getRank: Int = $(rank) /** - * Param for number of user blocks (>= 1). + * Param for number of user blocks (positive). * Default: 10 * @group param */ @@ -120,7 +120,7 @@ private[recommendation] trait ALSParams extends ALSModelParams with HasMaxIter w def getNumUserBlocks: Int = $(numUserBlocks) /** - * Param for number of item blocks (>= 1). + * Param for number of item blocks (positive). * Default: 10 * @group param */ @@ -141,7 +141,7 @@ private[recommendation] trait ALSParams extends ALSModelParams with HasMaxIter w def getImplicitPrefs: Boolean = $(implicitPrefs) /** - * Param for the alpha parameter in the implicit preference formulation (>= 0). + * Param for the alpha parameter in the implicit preference formulation (nonnegative). * Default: 1.0 * @group param */ @@ -174,7 +174,7 @@ private[recommendation] trait ALSParams extends ALSModelParams with HasMaxIter w /** * Param for StorageLevel for intermediate datasets. Pass in a string representation of - * [[StorageLevel]]. Cannot be "NONE". + * `StorageLevel`. Cannot be "NONE". * Default: "MEMORY_AND_DISK". * * @group expertParam @@ -188,7 +188,7 @@ private[recommendation] trait ALSParams extends ALSModelParams with HasMaxIter w /** * Param for StorageLevel for ALS model factors. Pass in a string representation of - * [[StorageLevel]]. + * `StorageLevel`. * Default: "MEMORY_AND_DISK". * * @group expertParam @@ -351,11 +351,11 @@ object ALSModel extends MLReadable[ALSModel] { * * For implicit preference data, the algorithm used is based on * "Collaborative Filtering for Implicit Feedback Datasets", available at - * [[http://dx.doi.org/10.1109/ICDM.2008.22]], adapted for the blocked approach used here. + * http://dx.doi.org/10.1109/ICDM.2008.22, adapted for the blocked approach used here. * * Essentially instead of finding the low-rank approximations to the rating matrix `R`, * this finds the approximations for a preference matrix `P` where the elements of `P` are 1 if - * r > 0 and 0 if r <= 0. The ratings then act as 'confidence' values related to strength of + * r > 0 and 0 if r <= 0. The ratings then act as 'confidence' values related to strength of * indicated user * preferences rather than explicit ratings given to items. */ diff --git a/mllib/src/main/scala/org/apache/spark/ml/tree/Node.scala b/mllib/src/main/scala/org/apache/spark/ml/tree/Node.scala index 8144bcb7d4..07e98a142b 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/tree/Node.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/tree/Node.scala @@ -145,8 +145,8 @@ class LeafNode private[ml] ( * Internal Decision Tree node. * @param prediction Prediction this node would make if it were a leaf node * @param impurity Impurity measure at this node (for training data) - * @param gain Information gain value. - * Values < 0 indicate missing values; this quirk will be removed with future updates. + * @param gain Information gain value. Values less than 0 indicate missing values; + * this quirk will be removed with future updates. * @param leftChild Left-hand child node * @param rightChild Right-hand child node * @param split Information about the test used to split to the left or right child. diff --git a/mllib/src/main/scala/org/apache/spark/ml/tree/Split.scala b/mllib/src/main/scala/org/apache/spark/ml/tree/Split.scala index 47fe3524f2..dff44e2d49 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/tree/Split.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/tree/Split.scala @@ -151,8 +151,8 @@ class CategoricalSplit private[ml] ( /** * Split which tests a continuous feature. * @param featureIndex Index of the feature to test - * @param threshold If the feature value is <= this threshold, then the split goes left. - * Otherwise, it goes right. + * @param threshold If the feature value is less than or equal to this threshold, then the + * split goes left. Otherwise, it goes right. */ class ContinuousSplit private[ml] (override val featureIndex: Int, val threshold: Double) extends Split { diff --git a/mllib/src/main/scala/org/apache/spark/ml/tree/treeModels.scala b/mllib/src/main/scala/org/apache/spark/ml/tree/treeModels.scala index 5b6fcc53c2..d3cbc36379 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/tree/treeModels.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/tree/treeModels.scala @@ -415,12 +415,12 @@ private[ml] object EnsembleModelReadWrite { /** * Helper method for loading a tree ensemble from disk. * This reconstructs all trees, returning the root nodes. - * @param path Path given to [[saveImpl()]] + * @param path Path given to `saveImpl` * @param className Class name for ensemble model type * @param treeClassName Class name for tree model type in the ensemble * @return (ensemble metadata, array over trees of (tree metadata, root node)), * where the root node is linked with all descendents - * @see [[saveImpl()]] for how the model was saved + * @see `saveImpl` for how the model was saved */ def loadImpl( path: String, diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/ChiSqSelector.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/ChiSqSelector.scala index c8c2823bba..56fb2d33c2 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/feature/ChiSqSelector.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/feature/ChiSqSelector.scala @@ -173,8 +173,8 @@ object ChiSqSelectorModel extends Loader[ChiSqSelectorModel] { * Creates a ChiSquared feature selector. * @param numTopFeatures number of features that selector will select * (ordered by statistic value descending) - * Note that if the number of features is < numTopFeatures, then this will - * select all features. + * Note that if the number of features is less than numTopFeatures, + * then this will select all features. */ @Since("1.3.0") class ChiSqSelector @Since("1.3.0") ( diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/PCA.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/PCA.scala index 15b72205ac..aaecfa8d45 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/feature/PCA.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/feature/PCA.scala @@ -70,7 +70,7 @@ class PCA @Since("1.4.0") (@Since("1.4.0") val k: Int) { } /** - * Java-friendly version of [[fit()]] + * Java-friendly version of `fit()`. */ @Since("1.4.0") def fit(sources: JavaRDD[Vector]): PCAModel = fit(sources.rdd) @@ -91,7 +91,7 @@ class PCAModel private[spark] ( * Transform a vector by computed Principal Components. * * @param vector vector to be transformed. - * Vector must be the same length as the source vectors given to [[PCA.fit()]]. + * Vector must be the same length as the source vectors given to `PCA.fit()`. * @return transformed vector. Vector will be of length k. */ @Since("1.4.0") diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/StandardScaler.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/StandardScaler.scala index b7d6c60568..3e86c6c59c 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/feature/StandardScaler.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/feature/StandardScaler.scala @@ -27,9 +27,8 @@ import org.apache.spark.rdd.RDD * Standardizes features by removing the mean and scaling to unit std using column summary * statistics on the samples in the training set. * - * The "unit std" is computed using the - * [[https://en.wikipedia.org/wiki/Standard_deviation#Corrected_sample_standard_deviation - * corrected sample standard deviation]], + * The "unit std" is computed using the corrected sample standard deviation + * (https://en.wikipedia.org/wiki/Standard_deviation#Corrected_sample_standard_deviation), * which is computed as the square root of the unbiased sample variance. * * @param withMean False by default. Centers the data with mean before scaling. It will build a diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Gini.scala b/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Gini.scala index 22e70278a6..c5e34ffa4f 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Gini.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/tree/impurity/Gini.scala @@ -20,8 +20,8 @@ package org.apache.spark.mllib.tree.impurity import org.apache.spark.annotation.{DeveloperApi, Since} /** - * Class for calculating the - * [[http://en.wikipedia.org/wiki/Decision_tree_learning#Gini_impurity Gini impurity]] + * Class for calculating the Gini impurity + * (http://en.wikipedia.org/wiki/Decision_tree_learning#Gini_impurity) * during multiclass classification. */ @Since("1.0.0") diff --git a/mllib/src/main/scala/org/apache/spark/mllib/util/modelSaveLoad.scala b/mllib/src/main/scala/org/apache/spark/mllib/util/modelSaveLoad.scala index 4d71d534a0..c881c8ea50 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/util/modelSaveLoad.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/util/modelSaveLoad.scala @@ -45,7 +45,7 @@ trait Saveable { * - human-readable (JSON) model metadata to path/metadata/ * - Parquet formatted data to path/data/ * - * The model may be loaded using [[Loader.load]]. + * The model may be loaded using `Loader.load`. * * @param sc Spark context used to save model data. * @param path Path specifying the directory in which to save this model. |